Add support for GPT-5.4 (#93)

Co-authored-by: Nigel Norris <ras@alghul.com>

README.md

@@ -116,6 +116,7 @@ curl http://127.0.0.1:8000/v1/chat/completions \
 - `gpt-5`
 - `gpt-5.1`
 - `gpt-5.2`
+- `gpt-5.4`
 - `gpt-5-codex`
 - `gpt-5.2-codex`
 - `gpt-5.3-codex`
@@ -128,9 +129,9 @@ curl http://127.0.0.1:8000/v1/chat/completions \
 
 ### Thinking effort
 
-- `--reasoning-effort` (choice of minimal,low,medium,high,xhigh)<br>
+- `--reasoning-effort` (choice of none,minimal,low,medium,high,xhigh)<br>
 GPT-5 has a configurable amount of "effort" it can put into thinking, which may cause it to take more time for a response to return, but may overall give a smarter answer. Applying this parameter after `serve` forces the server to use this reasoning effort by default, unless overrided by the API request with a different effort set. The default reasoning effort without setting this parameter is `medium`.<br>
-    The `gpt-5.1` family (including codex) supports `low`, `medium`, and `high` while `gpt-5.1-codex-max` adds `xhigh`. The `gpt-5.2` and `gpt-5.3` families (including codex) support `low`, `medium`, `high`, and `xhigh`. 
+    The `gpt-5.1` family (including codex) supports `low`, `medium`, and `high` while `gpt-5.1-codex-max` adds `xhigh`. The `gpt-5.2` and `gpt-5.3` families (including codex) support `low`, `medium`, `high`, and `xhigh`. GPT-5.4 supports `none`, `low`, `medium`, `high`, and `xhigh`.
 
 ### Thinking summaries
 

chatmock/cli.py

@@ -311,7 +311,7 @@ def main() -> None:
     )
     p_serve.add_argument(
         "--reasoning-effort",
-        choices=["minimal", "low", "medium", "high", "xhigh"],
+        choices=["none", "minimal", "low", "medium", "high", "xhigh"],
         default=os.getenv("CHATGPT_LOCAL_REASONING_EFFORT", "medium").lower(),
         help="Reasoning effort level for Responses API (default: medium)",
     )
@@ -335,7 +335,7 @@ def main() -> None:
         action="store_true",
         default=(os.getenv("CHATGPT_LOCAL_EXPOSE_REASONING_MODELS") or "").strip().lower() in ("1", "true", "yes", "on"),
         help=(
-            "Expose GPT-5 family reasoning effort variants (minimal|low|medium|high|xhigh where supported) "
+            "Expose GPT-5 family reasoning effort variants (none|minimal|low|medium|high|xhigh where supported) "
             "as separate models from /v1/models. This allows choosing effort via model selection in compatible UIs."
         ),
     )

chatmock/reasoning.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 from typing import Any, Dict, Set
 
 
-DEFAULT_REASONING_EFFORTS: Set[str] = {"minimal", "low", "medium", "high", "xhigh"}
+DEFAULT_REASONING_EFFORTS: Set[str] = {"minimal", "low", "medium", "high", "xhigh", "none"}
 
 
 def allowed_efforts_for_model(model: str | None) -> Set[str]:
@@ -11,6 +11,8 @@ def allowed_efforts_for_model(model: str | None) -> Set[str]:
     if not base:
         return DEFAULT_REASONING_EFFORTS
     normalized = base.split(":", 1)[0]
+    if normalized.startswith("gpt-5.4"):
+        return {"none", "low", "medium", "high", "xhigh"}
     if normalized.startswith("gpt-5.3"):
         return {"low", "medium", "high", "xhigh"}
     if normalized.startswith("gpt-5.2"):
@@ -103,7 +105,7 @@ def extract_reasoning_from_model_name(model: str | None) -> Dict[str, Any] | Non
     s = model.strip().lower()
     if not s:
         return None
-    efforts = {"minimal", "low", "medium", "high", "xhigh"}
+    efforts = {"minimal", "low", "medium", "high", "xhigh", "none"}
 
     if ":" in s:
         maybe = s.rsplit(":", 1)[-1].strip()
@@ -113,6 +115,8 @@ def extract_reasoning_from_model_name(model: str | None) -> Dict[str, Any] | Non
     for sep in ("-", "_"):
         if s.endswith(sep + "minimal"):
             return {"effort": "minimal"}
+        if s.endswith(sep + "none"):
+            return {"effort": "none"}
         if s.endswith(sep + "low"):
             return {"effort": "low"}
         if s.endswith(sep + "medium"):

chatmock/routes_ollama.py

@@ -97,6 +97,7 @@ def ollama_tags() -> Response:
         "gpt-5",
         "gpt-5.1",
         "gpt-5.2",
+        "gpt-5.4",
         "gpt-5.3-codex",
         "gpt-5-codex",
         "gpt-5.2-codex",
@@ -115,6 +116,11 @@ def ollama_tags() -> Response:
                 "gpt-5.1-high",
                 "gpt-5.1-medium",
                 "gpt-5.1-low",
+                "gpt-5.4-xhigh",
+                "gpt-5.4-high",
+                "gpt-5.4-medium",
+                "gpt-5.4-low",
+                "gpt-5.4-none",
                 "gpt-5.2-xhigh",
                 "gpt-5.2-high",
                 "gpt-5.2-medium",

chatmock/routes_openai.py

@@ -535,6 +535,7 @@ def list_models() -> Response:
         ("gpt-5", ["high", "medium", "low", "minimal"]),
         ("gpt-5.1", ["high", "medium", "low"]),
         ("gpt-5.2", ["xhigh", "high", "medium", "low"]),
+        ("gpt-5.4", ["xhigh", "high", "medium", "low", "none"]),
         ("gpt-5.3-codex", ["xhigh", "high", "medium", "low"]),
         ("gpt-5-codex", ["high", "medium", "low"]),
         ("gpt-5.2-codex", ["xhigh", "high", "medium", "low"]),

chatmock/upstream.py

@@ -42,6 +42,9 @@ def normalize_model_name(name: str | None, debug_model: str | None = None) -> st
         "gpt-5-latest": "gpt-5",
         "gpt-5": "gpt-5",
         "gpt-5.1": "gpt-5.1",
+        "gpt5.4": "gpt-5.4",
+        "gpt-5.4": "gpt-5.4",
+        "gpt-5.4-latest": "gpt-5.4",
         "gpt5.2": "gpt-5.2",
         "gpt-5.2": "gpt-5.2",
         "gpt-5.2-latest": "gpt-5.2",